AI Paper Atlas

Research map / Probabilistic and scientific modeling / Differential equations and PDEs

Laplace Meets Moreau: Smooth Approximation to Infimal Convolutions Using Laplace's Method

Ryan J. Tibshirani, Samy Wu Fung, Howard Heaton, Stanley Osher

JMLR 2025 · Probabilistic and scientific modeling › Differential equations and PDEs · approach: Neural PDE solvers · 6 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use more samples N in the Laplace approximationLaplace HJ approximation · Hamilton-Jacobi equation, d=2, p in {2,5,10}HJ residualImproved
increase smoothing parameter delta when samples are fewLaplace HJ approximation · Hamilton-Jacobi equation, few samplesHJ residualImproved
increase dimension from d=2 to larger dLaplace HJ approximation · Hamilton-Jacobi equation, d in {2,5,10}HJ residualHurt
use Laplace-proximal point instead of tuned gradient descentLaplace-proximal point · Benchmark suite, d=10 (ellipsoidal, discus)criterion valueImproved
use Laplace-proximal point instead of tuned gradient descentLaplace-proximal point · Benchmark suite, d=10 (rosenbrock, sharp ridge)criterion valueImproved
use Laplace-proximal point instead of gradient descent on the convex well-conditioned sphereLaplace-proximal point · Sphere benchmark, d=10criterion valueHurt
increase N and decrease delta in Laplace-proximal pointLaplace-proximal point · Weierstrass benchmark, d=10criterion valueNo clear effect
use Laplace-proximal point instead of random gradient-free oracle (N=1000)Laplace-proximal point · Benchmark suite, d=10, N=1000criterion valueMixed
average over multiple Gaussian draws in RGFRGF · Benchmark suite, d=10criterion valueImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy